Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Neural Relational Inference with Fast Modular Meta-learning (2310.07015v1)

Published 10 Oct 2023 in cs.LG

Abstract: \textit{Graph neural networks} (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions. \textit{Relational inference} is the problem of inferring these interactions and learning the dynamics from observational data. We frame relational inference as a \textit{modular meta-learning} problem, where neural modules are trained to be composed in different ways to solve many tasks. This meta-learning framework allows us to implicitly encode time invariance and infer relations in context of one another rather than independently, which increases inference capacity. Framing inference as the inner-loop optimization of meta-learning leads to a model-based approach that is more data-efficient and capable of estimating the state of entities that we do not observe directly, but whose existence can be inferred from their effect on observed entities. To address the large search space of graph neural network compositions, we meta-learn a \textit{proposal function} that speeds up the inner-loop simulated annealing search within the modular meta-learning algorithm, providing two orders of magnitude increase in the size of problems that can be addressed.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Modular meta-learning. In Proceedings of The 2nd Conference on Robot Learning, pp.  856–868, 2018.
  2. Graph element networks: adaptive, structured computation and memory. Proceedings of the 36th International Conference on Machine Learning-Volume 97, 2019.
  3. Neural module networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  39–48, 2016.
  4. A tutorial on adaptive mcmc. Statistics and computing, 18(4):343–373, 2008.
  5. Interaction networks for learning about objects, relations and physics. In Advances in neural information processing systems, pp.  4502–4510, 2016.
  6. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261, 2018.
  7. Meta-learning via learned loss. arXiv preprint arXiv:1906.05374, 2019.
  8. A meta-transfer objective for learning to disentangle causal mechanisms. CoRR, abs/1901.10912, 2019a.
  9. A meta-transfer objective for learning to disentangle causal mechanisms. arXiv preprint arXiv:1901.10912, 2019b.
  10. A compositional object-based approach to learning physical dynamics. arXiv preprint arXiv:1612.00341, 2016.
  11. Automatically composing representation transformations as a means for generalization. arXiv preprint arXiv:1807.04640, 2018.
  12. Learning quickly to plan quickly using modular meta-learning. arXiv preprint arXiv:1809.07878, 2018.
  13. Learning to adapt: Meta-learning for model-based control. In International Conference on Learning Representations, 2019.
  14. Rao-blackwellised particle filtering for dynamic bayesian networks. In Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence, pp.  176–183. Morgan Kaufmann Publishers Inc., 2000.
  15. Search, compress, compile: Library learning in neurally-guided bayesian program learning. In Advances in neural information processing systems, 2018.
  16. Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734, 2017.
  17. Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint arXiv:1703.03400, 2017.
  18. Learning discrete structures for graph neural networks. arXiv preprint arXiv:1903.11960, 2019.
  19. Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043, 2017.
  20. Neural message passing for quantum chemistry. arXiv preprint arXiv:1704.01212, 2017.
  21. A new model for learning in graph domains. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, volume 2, pp.  729–734, 2005.
  22. Relational inductive bias for physical construction in humans and machines. arXiv preprint arXiv:1806.01203, 2018.
  23. Junction tree variational autoencoder for molecular graph generation. arXiv preprint arXiv:1802.04364, 2018.
  24. Daniel D Johnson. Learning graphical state transitions. In International Conference on Learning Representations (ICLR), 2017.
  25. Adam: A method for stochastic optimization. CoRR, abs/1412.6980, 2014.
  26. Neural relational inference for interacting systems. arXiv preprint arXiv:1802.04687, 2018.
  27. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  28. Human-level concept learning through probabilistic program induction. Science, 350(6266):1332–1338, 2015.
  29. Ke Li and Jitendra Malik. Learning to optimize. arXiv preprint arXiv:1606.01885, 2016.
  30. Learning deep generative models of graphs. arXiv preprint arXiv:1803.03324, 2018a.
  31. Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. arXiv preprint arXiv:1810.01566, 2018b.
  32. Constrained graph variational autoencoders for molecule design. In NeurIPS, pp.  7806–7815, 2018.
  33. Adaptive mcmc with bayesian optimization. In Artificial Intelligence and Statistics, pp.  751–760, 2012.
  34. Beyond shared hierarchies: Deep multitask learning through soft layer ordering. arXiv preprint arXiv:1711.00108, 2017.
  35. A simple neural attentive meta-learner. In International Conference on Learning Representations (ICLR), 2018.
  36. Flexible neural representation for physics prediction. arXiv preprint arXiv:1806.08047, 2018.
  37. On first-order meta-learning algorithms. CoRR, abs/1803.02999, 2018. URL http://arxiv.org/abs/1803.02999.
  38. Automatic differentiation in PyTorch. In International Conference on Learning Representations, 2017.
  39. Learning compositional neural programs with recursive tree search and planning. arXiv preprint arXiv:1905.12941, 2019.
  40. Machine theory of mind. arXiv preprint arXiv:1802.07740, 2018.
  41. Optimization as a model for few-shot learning. In International Conference on Learning Representations (ICLR), 2017.
  42. Neural programmer-interpreters. arXiv preprint arXiv:1511.06279, 2015.
  43. Jürgen Schmidhuber. Evolutionary principles in self-referential learning, or on learning how to learn: the meta-meta-… hook. PhD thesis, Technische Universität München, 1987.
  44. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017.
  45. Graph refinement based tree extraction using mean-field networks and graph neural networks. arXiv preprint arXiv:1811.08674, 2018.
  46. Mastering the game of go without human knowledge. Nature, 550(7676):354, 2017.
  47. Graphvae: Towards generation of small graphs using variational autoencoders. In International Conference on Artificial Neural Networks, pp.  412–422. Springer, 2018.
  48. Stochastic prediction of multi-agent interactions from partial observations. arXiv preprint arXiv:1902.09641, 2019.
  49. How to grow a mind: Statistics, structure, and abstraction. science, 331(6022):1279–1285, 2011.
  50. Learning to learn. Springer Science & Business Media, 2012.
  51. Transfer learning. In Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp.  242–264. IGI Global, 2010.
  52. Relational neural expectation maximization: Unsupervised discovery of objects and their interactions. arXiv preprint arXiv:1802.10353, 2018.
  53. Matching networks for one shot learning. In Advances in Neural Information Processing Systems, pp.  3630–3638, 2016.
  54. Wilhelm von Humboldt. On language: On the diversity of human language construction and its influence on the mental development of the human species. Cambridge University Press, 1836/1999.
  55. Nervenet: Learning structured policy with graph neural networks. In International Conference on Learning Representations, 2018a.
  56. Meta-learning mcmc proposals. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (eds.), Advances in Neural Information Processing Systems 31, pp.  4146–4156. Curran Associates, Inc., 2018b.
  57. Learning actor relation graphs for group activity recognition. arXiv preprint arXiv:1904.10117, 2019a.
  58. A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596, 2019b.
  59. One-shot imitation from observing humans via domain-adaptive meta-learning. arXiv preprint arXiv:1802.01557, 2018.
  60. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434, 2018.
  61. Caml: Fast context adaptation via meta-learning. arXiv preprint arXiv:1810.03642, 2018.
Citations (55)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now